Is the Experiment Section Auditor skill free?

Yes. The skill itself is free from yujie-jason-zhang/polish_skill. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Experiment Section Auditor SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Experiment Section Auditor?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Experiment Section Auditor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Experiment Section Auditor

Audits a paper's experiment section for claim-anchored evidence, minimal ablations, and argument-style results.

by yujie-jason-zhang · yujie-jason-zhang/polish_skill

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · bda98da

Fed it a fake results paragraph claiming 91.2% accuracy plus unlisted 40%-noise and CIFAR-100 numbers: it flagged the missing parameter-matched ablation, the missing runtime measurement, AND caught that the narration cited results (40% noise, CIFAR-100) never listed among the stated done experiments -- a subtle fabrication risk a freeform review completely missed.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Experiment Section Auditor does

Maps every experiment and ablation to a main-line claim, flags orphaned claims and padding ablations, and rewrites report-style results prose ('Table X shows...') into claim-tied argument -- all without inventing experiments, feasibility, or results. Trigger it when revising an experiment section, ablation study, or results writeup and wanting an audit rather than a co-author.

How to install Experiment Section Auditor

git clone https://github.com/yujie-jason-zhang/polish_skill.git
mkdir -p ~/.claude/skills
cp -r polish_skill/experiment-section-auditor ~/.claude/skills/experiment-section-auditor

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Experiment Section Auditor

/experiment-section-auditor Audits a paper's experiment section for claim-anchored evidence, minimal ablations, and argument-style results.

It also activates on plain-language prompts like these:

Audit my experiment section, are these results tied to real claims?
Check if this ablation study is padding or actually necessary
Does my results paragraph cite numbers not in my experiment table?

Frequently asked questions

Is the Experiment Section Auditor skill free?: Yes. The skill itself is free from yujie-jason-zhang/polish_skill. SkillProof publishes the install command and an independent test verdict at no cost.
Does Experiment Section Auditor work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Fed it a fake results paragraph claiming 91.2% accuracy plus unlisted 40%-noise and CIFAR-100 numbers: it flagged the missing parameter-matched ablation, the missing runtime measurement, AND caught that the narration cited results (40% noise, CIFAR-100) never listed among the stated done experiments -- a subtle fabrication risk a freeform review completely missed.
What is the Experiment Section Auditor SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Experiment Section Auditor?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Experiment Section Auditor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.